© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3202
    Prev
    Next
    INDEX
    Explanations

    software-related terms and names, particularly those related to different Linux distributions and graphical user interfaces

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific software or operating system names related to Linux

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cott
    -0.87
    ilage
    -0.82
    ̶
    -0.78
    WHERE
    -0.77
    iologist
    -0.75
    indu
    -0.75
    ilater
    -0.74
    dinand
    -0.74
    Ñĭ
    -0.74
    busters
    -0.73
    POSITIVE LOGITS
     GNOME
    0.98
     KDE
    0.97
     Linux
    0.97
     GNU
    0.95
     desktop
    0.89
    Linux
    0.87
     Emacs
    0.87
    untu
    0.86
     Debian
    0.85
     Fedora
    0.82
    Activations Density 0.050%

    No Known Activations